Recent advances in FlowMatching-based Vision-Language-Action (VLA) frameworks have demonstrated remarkable advantages in generating high-frequency action chunks, particularly for highly dexterous robotic manipulation tasks. Despite these notable achievements, their practical applications are constrained by prolonged generation latency, which stems from inherent iterative sampling requirements and architectural limitations. To address this critical bottleneck, we propose a Mean-Flow based One-Step VLA approach. Specifically, we resolve the noise-induced issues in the action generation process, thereby eliminating the consistency constraints inherent to conventional Flow-Matching methods. This significantly enhances generation efficiency and enables one-step action generation. Real-world robotic experiments show that the generation speed of the proposed Mean-Flow based One-Step VLA is 8.7 times and 83.9 times faster than that of SmolVLA and Diffusion Policy, respectively. These results elucidate its great potential as a high-efficiency backbone for VLA-based robotic manipulation.
Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation
Department of Computing Science, University of Alberta(阿尔伯塔大学计算机科学系);National Research Council Canada(加拿大国家研究委员会);School of Electrical Engineering and Computer Science, University of Ottawa(渥太华大学电气工程与计算机科学学院);Vector Institute(向量研究所);Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所)
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics(库勒恩大学,机械工程系,机器人、自动化与机电一体化研究单位);KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images(库勒恩大学,电气工程系,语音和图像处理研究单位)
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
Li Auto Inc.(理想汽车);School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
Shanghai Qizhi Institute(上海期智研究院);The Chinese University of Hong Kong(香港中文大学);Hong Kong Embodied AI Lab(香港具身人工智能实验室);Tsinghua University(清华大学);University of California, Berkeley(加州大学伯克利分校)
DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
Institute of Trustworthy Embodied AI, Fudan University(可信具身AI研究院,复旦大学);Shanghai Key Laboratory of Multimodal Embodied AI(上海多模态具身AI重点实验室);City University of Hong Kong(香港城市大学)
CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models
University of Science and Technology of China (USTC)(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)
LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
Huazhong University of Science and Technology(华中科技大学);Beijing Zhongguancun Academy(北京中关村学院);Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究院);Harbin Institute of Technology(哈尔滨工业大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Zhengzhou University(郑州大学);Beihang University(北航);East China Normal University(东华大学);DeepCybot Co., Ltd.(DeepCybot有限公司)
ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations
Sichuan University(四川大学);Zhejiang University(浙江大学);Ludwig-Maximilians-Universität München(慕尼黑路德维希-马克西米利安大学);Lenovo Group Limited(联想集团有限公司);Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education(教育部机器学习与工业智能工程研究中心)
DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
Advanced Research Lab, Samsung R&D Institute China-Beijing (SRCB)(三星研发中心中国北京先进研究实验室);Samsung AI Center, DS Division(三星人工智能中心,DS部门);Hanyang University ERICA(翰洋大学ERICA)